Mobility Scooter User Driving Behavior Classification based on Deep Neural Networks

Abstract

A mobility scooter is an electrically powered scooter designed for people with restricted mobility [1] . The safety of mobility scooter driving is critical for drivers but often not assessed [2] , [3] . The goal of the project is to assess the safety level of people with neurological conditions driving mobility scooters by classifying their behaviors using mobility sensor data. In this work, we propose a data-driven approach to build time-series deep neural network models for mobility scooter driving behaviors, and thus based on mobility sensor data enable the real-time classification of 5 behaviors, i.e., sudden acceleration, Sudden left turn, Sudden right turn, Sudden break, and non-sudden movement.